KG-FGNN: Knowledge-guided GNN Foundation Model for Fertilisation-oriented Soil GHG Flux Prediction

2025-06-18

AI Summary

Accurate prediction of greenhouse gas (GHG) fluxes from agricultural soils is hindered by scarce, small-sample, and highly coupled multivariate agricultural data, limiting the performance of conventional machine learning models. Method: This paper proposes a knowledge-guided multi-objective, multi-graph graph neural network (GNN), integrating agricultural process model physics with data-driven learning. Specifically, it leverages process models to generate physically constrained synthetic data and employs an autoencoder for feature selection and compression; furthermore, it constructs a knowledge-embedded multi-graph structure to explicitly capture dynamic, heterogeneous couplings among diverse agro-environmental variables. Contribution/Results: Evaluated on simulated data from 47 countries and real-world farmland measurements, the method achieves a 12.6% improvement in prediction accuracy and a 23.4% gain in stability over state-of-the-art regression models. It significantly enhances generalizability and deployment feasibility under low-data regimes.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Precision soil greenhouse gas (GHG) flux prediction is essential in agricultural systems for assessing environmental impacts, developing emission mitigation strategies and promoting sustainable agriculture. Due to the lack of advanced sensor and network technologies on majority of farms, there are challenges in obtaining comprehensive and diverse agricultural data. As a result, the scarcity of agricultural data seriously obstructs the application of machine learning approaches in precision soil GHG flux prediction. This research proposes a knowledge-guided graph neural network framework that addresses the above challenges by integrating knowledge embedded in an agricultural process-based model and graph neural network techniques. Specifically, we utilise the agricultural process-based model to simulate and generate multi-dimensional agricultural datasets for 47 countries that cover a wide range of agricultural variables. To extract key agricultural features and integrate correlations among agricultural features in the prediction process, we propose a machine learning framework that integrates the autoencoder and multi-target multi-graph based graph neural networks, which utilises the autoencoder to selectively extract significant agricultural features from the agricultural process-based model simulation data and the graph neural network to integrate correlations among agricultural features for accurately predict fertilisation-oriented soil GHG fluxes. Comprehensive experiments were conducted with both the agricultural simulation dataset and real-world agricultural dataset to evaluate the proposed approach in comparison with well-known baseline and state-of-the-art regression methods. The results demonstrate that our proposed approach provides superior accuracy and stability in fertilisation-oriented soil GHG prediction.

Problem

• Predict soil GHG flux accurately for sustainable agriculture
• Overcome agricultural data scarcity with knowledge-guided GNN
• Integrate process-based models and GNNs for flux prediction

Innovation

• Knowledge-guided GNN integrates process-based models
• Autoencoder extracts key agricultural features
• Multi-graph GNN integrates feature correlations